Abstract
A novel automated framework for detecting and quantifying viability from agent enhanced cardiac magnetic resonance images is proposed. The framework identifies the pathological tissues based on a joint Markov–Gibbs random field (MGRF) model that accounts for the 1st-order visual appearance of the myocardial wall (in terms of the pixel-wise intensities) and the 2nd-order spatial interactions between pixels. The pathological tissue is quantified based on two metrics: the percentage area in each segment with respect to the total area of the segment, and the trans-wall extent of the pathological tissue. This transmural extent is estimated using point-to-point correspondences based on a Laplace partial differential equation. Transmural extent was validated using a simulated phantom. We tested the proposed framework on 14 datasets (168 images) and validated against manual expert delineation of the pathological tissue by two observers. Mean Dice similarity coefficients (DSC) of 0.90 and 0.88 were obtained for the observers, approaching the ideal value, 1. The Bland–Altman statistic of infarct volumes estimated by manual versus the MGRF estimation revealed little bias difference, and most values fell within the 95% confidence interval, suggesting very good agreement. Using the DSC measure we documented statistically significant superior segmentation performance for our MGRF method versus established intensity-based methods (greater DSC, and smaller standard deviation). Our Laplace method showed good operating characteristics across the full range of extent of transmural infarct, outperforming conventional methods. Phantom validation and experiments on patient data confirmed the robustness and accuracy of the proposed framework.
Similar content being viewed by others
Notes
For completeness, these modified EM-algorithms are posted on https://louisville.edu/speed/bioengineering/faculty/bioengineering-full/dr-ayman-elbaz/supplemental-materials.
More complete MLE descriptions are on https://louisville.edu/speed/bioengineering/faculty/bioengineering-full/dr-ayman-elbaz/supplemental-materials.
Abbreviations
- 2D:
-
Two-dimensional
- 3D:
-
Three-dimensional
- CE-CMR:
-
Contrast enhanced cardiac magnetic resonance
- DSC:
-
Dice similarity coefficient
- EM:
-
Expectation–maximization
- FN:
-
False negative
- FP:
-
False positive
- FWHM:
-
Full-width at half-maximum
- ICM:
-
Iterative conditional mode
- LCDG:
-
Linear combination of discrete Gaussians
- LCG:
-
Linear combination of Gaussians
- LV:
-
Left ventricle
- MAP:
-
Maximum a posteriori decision rule
- MGRF:
-
Markov–Gibbs random field
- MLE:
-
Maximum likelihood estimate
- PDE:
-
Partial differential equation
- SD:
-
Standard deviation
- TP:
-
True positive
References
Kühl HP, Beek AM, van der Weerdt AP, Hofman MB, Visser CA, Lammertsma AA, Heussen N, Visser FC, van Rossum AC (2003) Myocardial viability in chronic ischemic heart disease: comparison of contrast-enhanced magnetic resonance imaging with (18)F-fluorodeoxyglucose positron emission tomography. J Am Coll Cardiol 41(8):1341–1348
Dendale P, Franken PR, Block P, Pratikakis Y, De Roos A (1998) Contrast enhanced and functional magnetic resonance imaging for the detection of viable myocardium after infarction. Am Heart J 135:875–880
Klein C, Nekolla SG, Bengel FM, Momose M, Sammer A, Haas F, Schnackenburg B, Delius W, Mudra H, Wolfram D, Schwaiger M (2002) Assessment of myocardial viability with contrast-enhanced magnetic resonance imaging: comparison with positron emission tomography. Circulation 105(2):162–167
Gerber BL, Garot J, Bluemke DA, Wu KC, Lima JA (2002) Accuracy of contrast-enhanced magnetic resonance imaging in predicting improvement of regional myocardial function in patients after acute myocardial infarction. Circulation 106:1083–1089
Beek AM, Kühl HP, Bondarenko O, Twisk JWR, Hofman MBM, van Dockum WG, Visser CA, van Rossum AC (2003) Delayed contrast-enhanced magnetic resonance imaging for the prediction of regional functional improvement after acute myocardial infarction. J Am Coll Cardiol 42(5):895–901
van der Wall EE, Bax JJ (2008) Late contrast enhancement by CMR: more than scar? Int J Cardiovasc Imag 24(6):609–611
Kim RJ, Fieno DS, Parrish TB, Harris K, Chen E, Simonetti O, Bundy J, Finn P, Klocke FJ, Judd RM (1999) Relationship of MRI delayed contrast enhancement to irreversible injury, infarct age, and contractile function. Circulation 100(19):1992–2002
Fieno DS, Kim RJ, Chen E-L, Lomasney JW, Klocke FJ, Judd RM (2000) Contrast-enhanced magnetic resonance imaging of myocardium at risk: distinction between reversible and irreversible injury throughout infarct healing. J Am Coll Cardiol 36(6):1985–1991
Setser RM, Bexell DG, O’Donnell TP, Stillman AE, Lieber ML, Schoenhagen P, White RD (2003) Quantitative assessment of myocardial scar in delayed enhancement magnetic resonance imaging. J Magn Reson Imag 18(4):434–441
Amado L, Gerber B, Gupta S, Rettmann D, Szarf G, Schock R, Nasir K, Kraitchman D, Lima J (2004) Accurate and objective infarct sizing by contrast-enhanced magnetic resonance imaging in a canine myocardial infarction model. J Am Coll Cardiol 44:2383–2389
Hoffmann KR, Nazareth DP, Miskolczi L, Gopal A, Wang Z, Rudin S, Bednarek DR (2002) Vessel size measurements in angiograms: a comparison of techniques. Med Phys 29:1622–1633
Neizel M, Katoh M, Schade E, Rassaf T, Krombach GA, Kelm M, Kühl HP (2009) Rapid and accurate determination of relative infarct size in humans using contrast-enhanced magnetic resonance imaging. Clin Res Cardiol 98(5):319–324
Beek AM, Bondarenko O, Afsharzada F, van Rossum AC (2009) Quantification of late gadolinium enhanced CMR in viability assessment in chronic ischemic heart disease: a comparison to functional outcome. J Cardiovasc Magn Reson 11(1):6
Tao Q, Milles J, Zeppenfeld K, Lamb HJ, Bax JJ, Reiber JH, van der Geest RJ (2010) Automated segmentation of myocardial scar in late enhancement MRI using combined intensity and spatial information. Magn Reson Med 64(2):586–594
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst, Man Cybern 9:62–66
Heiberg E, Engblom H, Engvall J, Hedström E, Ugander M, Arheden H (2005) Semi-automatic quantification of myocardial infarction from delayed contrast enhanced magnetic resonance imaging. Scand Cardiovasc J 39(5):267–275
Hennemuth A, Seeger A, Friman O, Miller S, Klumpp B, Oeltze S, Peitgen H-O (2008) A comprehensive approach to the analysis of contrast enhanced cardiac MR images. IEEE Trans Med Imag 27(11):1592–1610
Elagouni K, Ciofolo-Veit C, Mory B (2010) Automatic segmentation of pathological tissues in cardiac MRI. In: Proceedings of IEEE international symposium biomedical imaging (ISBI’10): From Nano to Macro, Rotterdam, Netherlands, 14–17 April, pp 472–475
Noble N, Hill D, Breeuwer M, Razavi R (2004) The automatic identification of hibernating myocardium. In Proceedings of medical image computing computer-assisted intervention (MICCAI’04), vol. 3217, pp 890–898
Nazarian S, Bluemke DA, Lardo AC, Zviman MM, Watkins SP, Dickfeld TL, Meininger GR, Roguin A, Calkins H, Tomaselli GF, Weiss RG, Berger RD, Lima JA, Halperin HR (2005) Magnetic resonance assessment of the substrate for inducible ventricular tachycardia in nonischemic cardiomyopathy. Circulation 112(18):2821–2825
Sheehan FH, Bolson EL, Dodge HT, Mathey DG, Schofer J, Woo HW (1986) Advantages and applications of the centerline method for characterizing regional ventricular function. Circulation 74(2):293–305
McGillem MJ, Mancini GB, DeBoe SF, Buda AJ (1988) Modification of the centerline method for assessment of echocardiographic wall thickening and motion: a comparison with areas of risk. J Am Coll Cardiol 11(4):861–866
Schuijf JD, Kaandorp TA, Lamb HJ, van der Geest RJ, Viergever EP, van der Wall EE, de Roos A, Bax JJ (2004) Quantification of myocardial infarct size and transmurality by contrast-enhanced magnetic resonance imaging in men. Am J Cardiol 94(3):284–288
van Rugge FP, van der Wall EE, Spanjersberg SJ, de Roos A, Matheijssen NAA, Zwinderman AH, van Dijkman PRM, Reiber JHC, Bruschke AVG (1994) Magnetic resonance imaging during dobutamine stress for detection and localization of coronary artery disease quantitative wall motion analysis using a modification of the centerline method. Circulation 90(1):127–138
Elnakib A, Beache GM, Nitzken M, Gimel’farb G, El-Baz A (2011) A new framework for automated segmentation of left ventricle wall from contrast enhance cardiac magnetic resonance images. In Proceedings of IEEE international conference on image processing (ICIP’11), Brussels, Belgium, 11–14 Sept, pp 2337–2340
Dubes RC, Jain AK (1989) Random field models in image analysis. J Appl Stat 16:131–164
Gimel’farb G (1999) Image textures and Gibbs random fields. Kluwer Academic, Dordrecht
Besag J (1986) On the statistical analysis of dirty pictures. J R Stat Soc 48B(3):259–302
Gimel’farb G, Farag A, El-Baz A (2004), Expectation-maximization for a linear combination of gaussians. In Proceedings of IAPR international conference on pattern recognition (ICPR’04), Cambridge, UK, 23–26 Aug, 2004, pp 422–425
Webb A (2002) Statistical pattern recognition. Wiley, New York
Wu F-Y (1982) The Potts model. Rev Mod Phys 54(1):235–268
Farag AA, El-Baz A, Gimel’farb G (2006) Precise segmentation of multi-modal images. IEEE Trans Image Process 15(4):952–968
Dice LR (1945) Measures of the amount of ecologic association between species. Ecol Soc Am 26(3):297–302
Bland JM and Martin RW (1986), Statistical methods for assessing agreement between two methods of clinical measurement. Lancet i:307–310
Kim RJ, Wu E, Rafael A, Chen E-L, Parker MA, Simonetti O, Klocke FJ, Bonow RO, Judd RM (2000) The use of contrast-enhanced magnetic resonance imaging to identify reversible myocardial dysfunction. N Engl J Med 43(20):1445–1453
Cerqueira MD, Weissman NJ, Dilsizian V, Jacobs AK, Kaul S, Laskey WK, Pennell DJ, Rumberger JA, Ryan T, Verani MS (2002) Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart: a statement for healthcare professionals from the cardiac imaging committee of the council on clinical cardiology of the American heart association. Circulation 105(4):539–542
Choi K, Kim R, Gubernikoff G, Vargas J, Parker M, Judd R (2001) Transmural extent of acute myocardial infarction predicts long-term improvement in contractile function. Circulation 104(10):1101–1107
Jones S, Buchbinder B, Aharon I (2000) Three-dimensional mapping of cortical thickness using Laplace’s equation. Human Brain Map 11:12–32
Kim RJ, Shah DJ, Judd RM (2003) How we perform delayed enhancement imaging. J Cardiovasc MR 5(4):505–514
El-Baz A, Gimel’farb G, Falk R, Abou El-Ghar M, Kumar V, Heredia D (2009) A novel 3D joint Markov–Gibbs model for extracting blood vessels from PC-MRA images. In Proceedings of medical image computing computer-assisted intervention (MICCAI’09), vol. 5762, pp 943–950
Conflict of interest
None.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Elnakib, A., Beache, G.M., Gimel’farb, G. et al. New automated Markov–Gibbs random field based framework for myocardial wall viability quantification on agent enhanced cardiac magnetic resonance images. Int J Cardiovasc Imaging 28, 1683–1698 (2012). https://doi.org/10.1007/s10554-011-9991-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10554-011-9991-2